@inproceedings{berg-dalianis-2021-hb,
    title = "{HB} {D}eid - {HB} De-identification tool demonstrator",
    author = "Berg, Hanna  and
      Dalianis, Hercules",
    editor = "Dobnik, Simon  and
      {\O}vrelid, Lilja",
    booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
    month = may # " 31--2 " # jun,
    year = "2021",
    address = "Reykjavik, Iceland (Online)",
    publisher = {Link{\"o}ping University Electronic Press, Sweden},
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.nodalida-main.54/",
    pages = "467--471",
    abstract = "This paper describes a freely available web-based demonstrator called HB Deid. HB Deid identifies so-called protected health information, PHI, in a text written in Swedish and removes, masks, or replaces them with surrogates or pseudonyms. PHIs are named entities such as personal names, locations, ages, phone numbers, dates. HB Deid uses a CRF model trained on non-sensitive annotated text in Swedish, as well as a rule-based post-processing step for finding PHI. The final step in obscuring the PHI is then to either mask it, show only the class name or use a rule-based pseudonymisation system to replace it."
}